Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(56)

Side by Side Diff: components/autofill/core/browser/autofill_data_util_unittest.cc

Issue 2132103002: Split CJK full names into name parts correctly. (Closed) Base URL: https://chromium.googlesource.com/chromium/src.git@master
Patch Set: Improve precision for splitting Korean names. Created 4 years, 5 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch
OLDNEW
1 // Copyright 2016 The Chromium Authors. All rights reserved. 1 // Copyright 2016 The Chromium Authors. All rights reserved.
2 // Use of this source code is governed by a BSD-style license that can be 2 // Use of this source code is governed by a BSD-style license that can be
3 // found in the LICENSE file. 3 // found in the LICENSE file.
4 4
5 #include "components/autofill/core/browser/autofill_data_util.h" 5 #include "components/autofill/core/browser/autofill_data_util.h"
6 6
7 #include "base/strings/utf_string_conversions.h" 7 #include "base/strings/utf_string_conversions.h"
8 #include "components/autofill/core/browser/autofill_test_utils.h" 8 #include "components/autofill/core/browser/autofill_test_utils.h"
9 #include "testing/gtest/include/gtest/gtest.h" 9 #include "testing/gtest/include/gtest/gtest.h"
10 10
(...skipping 14 matching lines...) Expand all
25 {"Homer Jay Simpson", "Homer", "Jay", "Simpson"}, 25 {"Homer Jay Simpson", "Homer", "Jay", "Simpson"},
26 // No middle name. 26 // No middle name.
27 {"Moe Szyslak", "Moe", "", "Szyslak"}, 27 {"Moe Szyslak", "Moe", "", "Szyslak"},
28 // Common name prefixes removed. 28 // Common name prefixes removed.
29 {"Reverend Timothy Lovejoy", "Timothy", "", "Lovejoy"}, 29 {"Reverend Timothy Lovejoy", "Timothy", "", "Lovejoy"},
30 // Common name suffixes removed. 30 // Common name suffixes removed.
31 {"John Frink Phd", "John", "", "Frink"}, 31 {"John Frink Phd", "John", "", "Frink"},
32 // Exception to the name suffix removal. 32 // Exception to the name suffix removal.
33 {"John Ma", "John", "", "Ma"}, 33 {"John Ma", "John", "", "Ma"},
34 // Common family name prefixes not considered a middle name. 34 // Common family name prefixes not considered a middle name.
35 {"Milhouse Van Houten", "Milhouse", "", "Van Houten"}}; 35 {"Milhouse Van Houten", "Milhouse", "", "Van Houten"},
36
37 // CJK names have reverse order (surname goes first, given name goes
38 // second).
39 {"홍 길동", "길동", "", "홍"}, // Korean name, Hangul
40 {"孫 德明", "德明", "", "孫"}, // Chinese name, Unihan
41 {"山田 貴洋", "貴洋", "", "山田"}, // Japanese name, Unihan
42
43 // CJK names don't usually have a space in the middle, but most of the
44 // time, the surname is only one character (in Chinese & Korean).
45 {"최성훈", "성훈", "", "최"}, // Korean name, Hangul
46 {"강전희", "전희", "", "강"}, // Korean name, Hangul
47 {"刘翔", "翔", "", "刘"}, // (Traditional) Chinese name, Unihan
48 {"劉翔", "翔", "", "劉"}, // (Simplified) Chinese name, Unihan
gogerald1 2016/07/14 18:28:52 nit: I believe this ("劉") is traditional and above
nicolaso 2016/07/14 20:32:17 Fixed.
49
50 // There are a few exceptions. Occasionally, the surname has two
51 // characters.
52 {"남궁도", "도", "", "남궁"}, // Korean name, Hangul
53 {"황보혜정", "혜정", "", "황보"}, // Korean name, Hangul
54 {"歐陽靖", "靖", "", "歐陽"}, // (Traditional) Chinese name, Unihan
55
56 // Korean full names always have at least 3 characters, so a 2-character
Jinsuk Kim 2016/07/13 21:51:09 Please update the comment here.
nicolaso 2016/07/14 18:12:43 Done.
57 // name can only be a given name. Chinese full names, however, might be
58 // only 2 characters.
59 {"제동", "제동", "", ""}, // Korean name, Hangul
60 {"孫文", "文", "", "孫"} // Chinese name, Unihan
61 };
36 62
37 for (TestCase test_case : test_cases) { 63 for (TestCase test_case : test_cases) {
38 NameParts name_parts = SplitName(base::UTF8ToUTF16(test_case.full_name)); 64 NameParts name_parts = SplitName(base::UTF8ToUTF16(test_case.full_name));
39 65
40 EXPECT_EQ(base::UTF8ToUTF16(test_case.given_name), name_parts.given); 66 EXPECT_EQ(base::UTF8ToUTF16(test_case.given_name), name_parts.given);
41 EXPECT_EQ(base::UTF8ToUTF16(test_case.middle_name), name_parts.middle); 67 EXPECT_EQ(base::UTF8ToUTF16(test_case.middle_name), name_parts.middle);
42 EXPECT_EQ(base::UTF8ToUTF16(test_case.family_name), name_parts.family); 68 EXPECT_EQ(base::UTF8ToUTF16(test_case.family_name), name_parts.family);
43 } 69 }
44 } 70 }
45 71
(...skipping 13 matching lines...) Expand all
59 85
60 EXPECT_TRUE( 86 EXPECT_TRUE(
61 ProfileMatchesFullName(base::UTF8ToUTF16("First M. Last"), profile)); 87 ProfileMatchesFullName(base::UTF8ToUTF16("First M. Last"), profile));
62 88
63 EXPECT_FALSE( 89 EXPECT_FALSE(
64 ProfileMatchesFullName(base::UTF8ToUTF16("Kirby Puckett"), profile)); 90 ProfileMatchesFullName(base::UTF8ToUTF16("Kirby Puckett"), profile));
65 } 91 }
66 92
67 } // namespace data_util 93 } // namespace data_util
68 } // namespace autofill 94 } // namespace autofill
OLDNEW

Powered by Google App Engine
This is Rietveld 408576698